Skip to content

[MRG + 1] MNT Platform independent hash collision tests in FeatureHasher #9710

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 12, 2017
Merged

[MRG + 1] MNT Platform independent hash collision tests in FeatureHasher #9710

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4f55747
More robust hash collision tests in the FeatureHasher
rth Sep 8, 2017
c637174
Use larger vocabulary for the hash collistion tests
rth Sep 8, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 24 additions & 9 deletions sklearn/feature_extraction/tests/test_feature_hasher.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,30 +112,45 @@ def test_hasher_zeros():

@ignore_warnings(category=DeprecationWarning)
def test_hasher_alternate_sign():
# the last two tokens produce a hash collision that sums as 0
X = [["foo", "bar", "baz", "investigation need", "records"]]
X = [list("Thequickbrownfoxjumped")]

Xt = FeatureHasher(alternate_sign=True, non_negative=False,
input_type='string').fit_transform(X)
assert_true(Xt.data.min() < 0 and Xt.data.max() > 0)
# check that we have a collision that produces a 0 count
assert_true(len(Xt.data) < len(X[0]))
assert_true((Xt.data == 0.).any())
assert Xt.data.min() < 0 and Xt.data.max() > 0

Xt = FeatureHasher(alternate_sign=True, non_negative=True,
input_type='string').fit_transform(X)
assert_true((Xt.data >= 0).all()) # all counts are positive
assert_true((Xt.data == 0.).any()) # we still have a collision
assert Xt.data.min() > 0

Xt = FeatureHasher(alternate_sign=False, non_negative=True,
input_type='string').fit_transform(X)
assert_true((Xt.data > 0).all()) # strictly positive counts
assert Xt.data.min() > 0
Xt_2 = FeatureHasher(alternate_sign=False, non_negative=False,
input_type='string').fit_transform(X)
# With initially positive features, the non_negative option should
# have no impact when alternate_sign=False
assert_array_equal(Xt.data, Xt_2.data)


@ignore_warnings(category=DeprecationWarning)
def test_hash_collisions():
X = [list("Thequickbrownfoxjumped")]

Xt = FeatureHasher(alternate_sign=True, non_negative=False,
n_features=1, input_type='string').fit_transform(X)
# check that some of the hashed tokens are added
# with an opposite sign and cancel out
assert abs(Xt.data[0]) < len(X[0])

Xt = FeatureHasher(alternate_sign=True, non_negative=True,
n_features=1, input_type='string').fit_transform(X)
assert abs(Xt.data[0]) < len(X[0])

Xt = FeatureHasher(alternate_sign=False, non_negative=True,
n_features=1, input_type='string').fit_transform(X)
assert Xt.data[0] == len(X[0])


@ignore_warnings(category=DeprecationWarning)
def test_hasher_negative():
X = [{"foo": 2, "bar": -4, "baz": -1}.items()]
Expand Down